hfl/llama-3-chinese-8b-instruct-v2

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:8BQuant:FP8Ctx Length:8kPublished:May 7, 2024License:apache-2.0Architecture:Transformer0.0K Open Weights Warm

hfl/llama-3-chinese-8b-instruct-v2 is an 8 billion parameter instruction-tuned language model developed by hfl, based on Meta-Llama-3-8B-Instruct. This model is specifically fine-tuned with 5 million Chinese instruction data, making it highly optimized for conversational AI and question-answering tasks in Chinese. It leverages an 8192-token context length to provide robust performance for various Chinese language applications.

Loading preview...

Model Overview

hfl/llama-3-chinese-8b-instruct-v2 is an 8 billion parameter instruction-tuned language model built upon Meta's Llama-3-8B-Instruct architecture. Developed by hfl, this model is specifically enhanced for Chinese language applications through direct tuning with 5 million instruction data points.

Key Capabilities

  • Chinese Instruction Following: Optimized for understanding and responding to instructions in Chinese.
  • Conversational AI: Designed for engaging in natural conversations.
  • Question Answering: Proficient in answering queries based on provided context or general knowledge.
  • Llama-3 Base: Benefits from the strong foundational capabilities of the Meta-Llama-3-8B-Instruct model.

Use Cases

This model is particularly well-suited for:

  • Developing Chinese chatbots and virtual assistants.
  • Implementing Chinese language question-answering systems.
  • Applications requiring instruction-following in Chinese.

For more detailed information on performance and usage, refer to the GitHub project page.

Popular Sampler Settings

Top 3 parameter combinations used by Featherless users for this model. Click a tab to see each config.

temperature
top_p
top_k
frequency_penalty
presence_penalty
repetition_penalty
min_p